AGENTKERNEL
- Home
- All models
- Qwen3 235B A22B Thinking 2507
Qwen3 235B A22B Thinking 2507: price, performance and context
Open Qwen3 235B A22B Thinking 2507 by Qwen costs $0.45 per 1M input and $3.50 per 1M output tokens, handles up to 128K tokens in one request (≈ 380 pages of text) and scores 12.7 points on the AgentKernel performance index, rank 132 of 212.
Privacy: zero data retention with one provider, not in the EU. Availability over the last 24 h: 75%.
Open in the interactive comparisonKey facts
- Licence
- Open weights: free to download and self-host
- Input / 1M tokens
- $0.45
- Output / 1M tokens
- $3.50
- Context window
- 128K tokens
- Max. output
- 16.4K tokens
- Performance index
- 12.7 points · rank 132 of 212
- Coding index
- 22.1 points · rank 94 of 119
- Agentic index
- 1.3 points · rank 73 of 91
- Cost at your usage
- $1.325 / month
- Knowledge cutoff
- Jun 2025
- In the catalog since
- Jul 25, 2025
- Capabilities
- Reasoning, Tool Calling
What do you get for $10.00?
Rules of thumb from the cost calculator, base rates without caching or taxes.
| Task | Cost per task | For $10.00 |
|---|---|---|
| Chat repliesA question with a short history, a detailed answer | $0.002 | 5,300 |
| Email draftsBullet points in, a finished email out | $0.002 | 6,600 |
| Document summariesRead 10 pages, write a one-page summary | $0.003 | 3,100 |
| Code reviewsReview and comment on 500 lines of code | $0.006 | 1,700 |
| Book analysesAnalyse a 300-page book in one go | $0.052 | 190 |
Cheaper with similar performance
| Model | Licence | Performance | Your cost / month |
|---|---|---|---|
| Ling 3.1 FlashinclusionAI | Proprietary | 41.1 | $0.00 |
| Ling 3.0 Flash VLinclusionAI | Open | 24.6 | $0.036 |
| Ling 3.0 FlashinclusionAI | Open | 20.1 | $0.037 |
Stronger models
| Model | Licence | Performance | Your cost / month |
|---|---|---|---|
| Nemotron 3 SuperNVIDIA | Open | 12.8 | $0.193 |
| GLM 4.5Z.ai | Open | 12.8 | $1.15 |
| Nemotron 3.5 LightningNVIDIA | Open | 12.9 | $0.08 |